OpenRouter's most-used application by token volume — over 17 trillion tokens processed — Hermes Agent is an open-source autonomous agent built by Nous Research that lives on your server and gets more capable every day. Define a goal in natural language and Hermes plans sub-tasks, executes them through tool integrations, observes results, handles errors, and refines until the job is done or it genuinely needs your input. Persistent memory with full-text search and LLM summarization lets it recall context across sessions, and an agent-created skills system self-improves after complex tasks. A messaging gateway connects Telegram, Discord, Slack, WhatsApp, Signal, and 16 more platforms with cross-channel conversation continuity. A built-in cron scheduler runs daily reports, nightly backups, and weekly audits unattended. Subagent spawning parallelizes workstreams, and six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona — fit any infrastructure. Works with any LLM provider: Nous Portal, OpenRouter for 400+ models from 70+ providers, OpenAI, Anthropic, or your own endpoint. The API key you supply powers all LLM calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A personal AI assistant that remembers what it learns and reaches you wherever you are — OpenClaw is an open-source agent gateway built by the OpenClaw Foundation with 247,000+ GitHub stars. It connects to 200+ LLM models through providers like Anthropic, OpenRouter, and OpenAI, and meets you on 21+ messaging channels: Telegram, Slack, Discord, WhatsApp, Signal, iMessage, Matrix, and more. Persistent memory with full-text search lets the agent recall context across sessions, and a self-improving skills system means it gets more capable the longer it runs. Voice wake words and talk mode enable hands-free interaction on macOS, iOS, and Android. A live canvas provides an agent-driven visual workspace. Built-in browser automation, cron scheduling for unattended tasks, and subagent spawning for parallel workstreams round out the toolset. The gateway architecture keeps all sessions, credentials, and conversation history on your own server — nothing transits a third-party cloud unless you choose to connect one. The API key you provide for your chosen LLM provider powers the underlying calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Perplexity's answer-engine experience, self-hostable and open-source: Morphic searches the web and writes cited answers. Instead of returning a list of links, it searches the web, reads the sources, and generates a complete answer with inline numbered citations. The generative UI streams rich components, source cards with thumbnails, image grids, syntax-highlighted code, and LaTeX math, rather than plain markdown. Quick mode answers fast; Adaptive mode runs deeper multi-step research. Search backends are pluggable: the Docker Compose bundle ships with a private SearXNG instance so no search API key is required, and Tavily, Brave, and Exa are supported alternatives. LLM providers include OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible endpoint, with per-mode model mapping - fast, cheap models for quick searches, stronger models for adaptive research, tuning the cost-quality trade-off per query type. An inspector panel exposes tool execution during multi-step research, and AI-suggested follow-up questions keep an investigation moving. Chat history persists in PostgreSQL, results are shareable by URL, file uploads feed context into queries, and optional Supabase authentication adds multi-user or guest access. Because the default search path is your private SearXNG instance, research topics never hit a commercial search API - and with local Ollama models the marginal cost of a query approaches zero. Built with Next.js, TypeScript, and the Vercel AI SDK under Apache 2.0.

Every major model provider behind one ChatGPT-style interface: LibreChat spans OpenAI, Anthropic, Google, Azure, AWS Bedrock, Vertex AI, Groq, Mistral, OpenRouter, DeepSeek, and any OpenAI-compatible endpoint including local Ollama. You can switch models mid-conversation and compare providers without changing tools. Its Agents framework builds no-code custom assistants with tool access via Model Context Protocol servers, file search over uploaded documents through an optional pgvector-backed RAG service, and a sandboxed Code Interpreter that executes Python, JavaScript, Go, C++, Java, PHP, and Rust. Artifacts render React components, HTML, and Mermaid diagrams directly in chat, and image generation works through DALL-E and other configured providers. Multi-user support is enterprise-grade, with OAuth, SAML, LDAP, and two-factor authentication, per-user conversation history in MongoDB, and Meilisearch-powered search across all messages and files, plus reusable presets, forkable threads, and persistent memory across conversations. The economics favor teams: instead of a ChatGPT Plus seat per person, everyone shares one instance billed per API token, with access to every provider rather than one - and providers see individual API calls, not your accumulated organizational knowledge. Deployment is Docker Compose; API keys and endpoints are configured through .env and librechat.yaml.

Get ready to tap into the pulse of your customer base with Fider, the idea wrangler extraordinaire! This app is like a digital town hall where your users can shout out their brilliant ideas, give a thumbs-up to their favorites, and engage in riveting discussions about their most-wanted features. Fider is the ultimate feedback funnel, keeping you in the know with the who's who of suggestions – whether they're hot off the press, in the works, or given the polite 'thanks, but no thanks.' With a sign-in faster than a superhero's costume change, your visitors can jump right into the action. Dress Fider up to match your brand's snazzy style, or go incognito with a private site for your eyes only. Speaking the language of the people (multiple languages, to be exact), Fider breaks down barriers like a linguistic ninja. Tagging? Check. Markdown flair? Double-check. A public API that plays nice with other systems? You betcha. And for the tech-savvy, there's even a Webhook handshake for seamless integrations. Hosted on RepoCloud, where the cost is as friendly as your neighborhood barista, Fider turns feedback chaos into a harmonious chorus of actionable insights. So why wait? Let Fider and RepoCloud be the dynamic duo your audience has been waiting for!

Meet your new digital sidekick, a fully autonomous AI Agent ready to tackle complex tasks and projects across terminals, browsers, and editors. It's like having a super-smart assistant who never needs coffee breaks!

Where Miniflux strips reading down, FreshRSS gives you knobs - the feature-rich pole of self-hosted RSS, comfortable with thousands of feeds. It's a multi-user PHP aggregator (host family and friends on one instance, with an anonymous reading mode) with the reading workflow refined over a decade: favorites, custom tags, powerful filter and search queries, three reading views, and statistics that reveal each site's publishing frequency - useful for pruning subscriptions. Two properties make it the standard choice. First, the Google Reader-compatible API (plus a Fever API) syncs with virtually every serious RSS client - Reeder, NetNewsWire, ReadYou, FeedMe, Fluent Reader - so your phone reads from your server. Second, native WebSub support means compatible sources (WordPress, Blogger, Medium, Friendica) push new articles instantly instead of waiting for polling. A 50+ extension ecosystem adds what truncated feeds omit - full-text content fetching, reading-time estimates, trending views, auto-unsubscribe for dead feeds - alongside community themes and custom CSS. OPML import/export keeps subscriptions portable, a CLI handles administration, and article sharing posts to many services. AGPL-licensed, running on SQLite, MySQL, or PostgreSQL. Feedly Pro's feature set, minus Feedly's subscription and its algorithms.

One statically-compiled Go binary over PostgreSQL, no ORM, no framework, static assets embedded in the executable: Miniflux is the minimalist, opinionated feed reader. The opinions are the feature: page layout, fonts, and colors are tuned for reading, and everything else is treated as noise. It consumes Atom, RSS, and JSON Feed formats with OPML import/export, organizes articles with categories and bookmarks, fetches original full-text content for summary-only feeds, and provides Postgres-powered full-text search. Privacy work happens automatically: pixel trackers are stripped, tracking parameters removed from URLs, a media proxy blocks third-party tracking, referrers are never forwarded, and there is zero telemetry. Navigation is keyboard-first - j/k through items, o to open, f to star - with touch gestures on mobile. Podcast, video, and music enclosures are supported, and YouTube videos play inline. Over 25 integrations save articles onward to Wallabag, Readwise Reader, Pinboard, Linkding, Instapaper, Notion, Telegram, Matrix, Ntfy, and more, plus webhooks and a REST API with Go and Python clients; the Google Reader API endpoint supports existing mobile reader apps. Authentication spans local passwords, passkeys (WebAuthn), Google OAuth2, OpenID Connect, and reverse-proxy headers. It is Apache 2.0 licensed, translated into 20 languages, and updates feeds on an internal scheduler.

Why should your chat history live on someone else's servers? Chatpad AI - a React/TypeScript front end for the OpenAI API, built on the Mantine component library - is designed around that question. Enter your own OpenAI API key and start chatting with GPT models; every conversation, prompt, and setting is stored locally in your browser via DexieJS over IndexedDB, with no tracking, no cookies, and no backend database at all. That architecture is the point - the Docker image is just Nginx serving static files, making it one of the lightest AI deployments in the catalog, and pay-per-token API pricing typically undercuts a ChatGPT Plus subscription for moderate use. The interface earns its "premium quality" tagline with the details: a persona selector that switches communication styles per conversation, a saved-prompts library for messages you reuse constantly, organized chat history, and full data export/import so conversations move between browsers or into backups as files you control. A JSON config file customizes defaults - models, API endpoints, UI options - without rebuilding the image. AGPL-licensed, with desktop builds available upstream. For teams that want ChatGPT's utility with a self-hosted, zero-telemetry footprint, Chatpad is the minimal, sane answer.

Hold Alt/Option, click any string in your running app, and edit the translation in place: Tolgee is an open-source localization platform built the way developers wish translation worked - changes save straight to the platform with no hunting through JSON or PO files. In-context editing works even in production via the Tolgee Tools browser extension, which injects credentials without touching source code, so a client or colleague with zero coding skills can translate the product inside the product. The SDKs (React, Angular, Vue, Svelte, plus iOS and Android) extract context from each UI element and capture one-click screenshots, giving both human translators and machines the surrounding meaning that raw string files lose. Autonomous translation uses that context: new keys are instantly filled from translation memory or machine translation (DeepL, Google Translate, AWS Translate), with optional human review afterward - shipping no longer waits on a translation agency. A CLI handles import/export, a REST API covers automation, a Figma plugin bridges design, and an MCP server lets AI coding assistants search keys, create translations, and trigger machine translation without leaving the editor. Self-hosting this Crowdin/Phrase/Lokalise alternative keeps every string, screenshot, and API key on your infrastructure.

Quote to cash in one web application - create quotes, convert them to invoices, record payments, track customers: iDURAR is an open-source ERP and CRM platform for small and medium-sized businesses. Built on the MERN stack (MongoDB, Express, React, Node.js) with Ant Design components and Redux state management, it presents a clean SaaS-style interface that needs little onboarding. Core modules cover invoice management with PDF generation and email delivery, payment recording against invoices, quote and proforma handling, customer records, and accounting views over the resulting data. Multi-currency support and localization make it usable for internationally operating teams. Because the whole stack is JavaScript with an API-first backend, extending it - custom fields, new modules, integrations - is approachable for any Node/React developer rather than requiring a specialist ERP skill set. Deployment is straightforward via Docker with a MongoDB instance. Licensed under AGPL-3.0 with free commercial use; a hosted enterprise version exists but the self-hosted edition is fully functional.

Personal, minimalist, database-free bookmarking - Shaarli is a philosophy as much as an app. Everything lives in a single compressed datastore file inside data/: no MySQL, no PostgreSQL, backup by copying one directory. That write-once/read-many file is usually served straight from OS disk caches, which is why a decade-old Shaarli instance with tens of thousands of links still responds instantly. Designed deliberately single-user, it saves URL, title, unlimited-length description, and tags (with autocomplete, renaming, and merging), marks entries public or private, and automatically strips utm_source and fb tracking parameters from saved URLs. That description field is why the community uses Shaarli as far more than bookmarks: a microblog, read-it-later queue, code-snippet base, pastebin, and shared clipboard between machines. Sharing is one click via bookmarklet or Android apps; consumption is per-tag RSS/Atom feeds plus a daily digest feed; search is full-text with tag filtering. A REST API opens it to any client, a plugin and theme system extends the PHP core (Markdown rendering, thumbnails), and import/export uses browser-standard Netscape HTML - your data enters and leaves freely. LDAP login is supported, no telemetry is sent anywhere, and the UI degrades gracefully without JavaScript. The anti-cloud Delicious.

Paste some text, hit save, share the link - Hasty Paste is a fast, minimal pastebin written in Python on the async Quart framework, named, by its author's own admission, "because you use it so fast without a care in the world." No accounts, no authentication, no friction - built for the everyday case of handing a debug log, config snippet, or stack trace to someone in tech support or a chat channel. Pastes get randomly generated IDs, with an optional "long" ID mode that makes brute-force URL guessing impractical, and expiry times ensure throwaway content actually gets thrown away. Optional Pygments syntax highlighting makes code readable, a dark theme spares your eyes, and the whole interface works without JavaScript - it renders in terminal browsers and under the strictest script blockers. Storage is a custom flat-file system (no database), caching runs internally or through Redis for busier instances, and a REST API plus the companion "Hastily Paste It" CLI script enable piping command output straight into a paste from the terminal. The Alpine-based Docker image is tiny, resource usage is minimal, and the license is AGPL.

Get ready to teleport your desktop experience with Remmina, the Swiss Army knife of remote desktop clients! Perfect for the digital nomad or the midnight-oil-burning sysadmin, Remmina lets you juggle multiple remote machines like a circus performer, with a smorgasbord of network protocols at your fingertips - RDP, VNC, SPICE, you name it! Crafted with love in GTK, it's as comfy on a jumbotron as it is on a pocket-sized screen. Dive in at http://yourhost:3000/ or take the secure plunge via https://yourhost:3001/. And thanks to its Docker Baseimage KasmVNC heritage, you can toggle features like a light switch, customizing your remote control experience. Host it on RepoCloud, and you'll save enough to treat yourself to a fancy coffee - because who needs overpriced cloud hosting when you've got the open-source haven of RepoCloud?

Get ready to surf the digital waves with Opera, the web browser that's like the Swiss Army knife of internet exploration! This isn't just any Chromium-based browser; it's like Chromium went to the gym, got a makeover, and learned a few new party tricks. You can catch this browser flexing its muscles at http://yourhost:3000/ or showing off its secure https moves at https://yourhost:3001/. Craving pixel perfection? Crank up the Stream Quality to 'Lossless' and watch as Opera delivers a visual feast, smoother than a buttered-up otter on a water slide. Fancy yourself a bit of a command-line cowboy? Saddle up and throw as many Chromium CLI flags as you can lasso, and Opera will gallop along without breaking a sweat. And because we know you like to keep things running smoother than a dolphin's dome, Opera on RepoCloud sidesteps those pesky permission squabbles between host OS and container with a simple tip of the hat to user PUID and group PGID. So why settle for basic browsing when you can have the full Opera experience on RepoCloud, where the cost is as tiny as a flea's waistcoat?

Team and product documentation on a fast Vue frontend with PostgreSQL storage: Wiki.js is a Node.js wiki engine. Its distinguishing trait is per-page editor choice: authors pick Markdown with live preview, a WYSIWYG visual builder for non-technical writers, or raw HTML, page by page. Native Git synchronization commits every page change to GitHub, GitLab, Bitbucket, Azure DevOps, or any Git remote - bi-directionally, so edits made in the repository flow back into the wiki - giving documentation version-controlled backup for free. Authentication coverage is among the broadest of any self-hosted wiki: local accounts with self-registration, social login via Google, GitHub, Discord, and Slack, and enterprise SSO through LDAP/Active Directory, SAML, CAS, Auth0, Okta, Azure AD, Keycloak, and generic OAuth2/OIDC, with optional MFA. Built-in full-text search runs on PostgreSQL with zero setup, and external engines like Algolia or Solr can substitute. Page history with visual version comparison, granular group-based permissions per path, nested navigation menus, 50+ integration modules, and full localization round it out. AGPLv3-licensed with a 28k-star community.

Get ready to turbocharge your torrenting experience with SimpleTorrent, the self-hosted torrent maestro that lets you kick back while your torrents do the hustle. Crafted with the magic of Go (golang), this nifty app transforms your server into a torrent-fetching powerhouse, snagging files and lining them up for your streaming pleasure or HTTP retrieval. Fancy a bit of control? You got it! Pick and choose individual files, command an external app to celebrate task completion, and enforce a seeding etiquette to say 'stop' when you've shared enough. But wait, there's more! Throttle those speeds to avoid hogging the bandwidth and dive into the nitty-gritty of transfer stats with a web UI that's slicker than a greased otter. Real-time updates? Check. Mobile-friendly? You bet. A content server that's faster than a caffeinated cheetah? Absolutely. And with IPv6 readiness, a fresh torrent engine from anacrolix/torrent, and extra goodies like a torrent watcher, K8s/docker health-checks, bonus trackers, and a magnet protocol handler, SimpleTorrent hosted on RepoCloud is like having your very own torrent butler – all at a price that won't plunder your coin purse!

A server full of scattered services becomes one clean application hub under Flame - a self-hosted startpage where every bit of configuration happens in built-in GUI editors, never a config file. Applications and bookmarks are created, edited, and organized into categories directly in the browser, and favorites pin to the homescreen for one-click access. The integrated search bar filters your apps and bookmarks locally as you type, and prefix shortcuts (like /g for Google) route queries to any of 11 web search providers or custom ones you define, making Flame a genuine browser homepage rather than a static link wall. Docker integration is the standout for homelabs: mount the Docker socket, add flame.type, flame.name, and flame.url labels to containers, and new services appear on the dashboard automatically - Kubernetes Ingress annotations work the same way. A weather widget shows temperature, cloud coverage, and animated conditions for your coordinates, and password authentication protects settings and items. Appearance is deeply customizable with 15 built-in color themes, a custom theme builder, and full custom CSS support. The stack is Node.js with SQLite behind a React frontend - light, fast, and inspired by the minimalist SUI design.